A Study on a Real-World Data-Based VTE Risk Prediction Model for Lymphoma Patients

Changli He¹Yin Wang¹Han Zhang¹Sitian Li¹Fengjiao Kang²Fengqun Cai¹Lizhu Han³Qinan Yin³Gang Li^3*Xuewu Song^3*Bian Yuan^3*

• ¹School of Medicine, University of Electronic Science and Technology of China, chengdu, China
• ²Traditional Chinese Medicine Hospital of Xinjiang Uyghur Autonomous Region, Urumqi, China
• ³Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China

Background: Patients diagnosed with malignant tumors exhibit a markedly elevated risk of venous thromboembolism (VTE), which has a negative impact on their prognosis. Currently, there is no reliable predictive model specifically for thrombosis risk in lymphoma patients. This study aims to develop and validate a machine learning model leveraging real-world data, offering a dependable risk assessment tool for the early identification of VTE in lymphoma patients. Methods: We retrospectively analyzed 605 hospitalized patients with lymphoma between January 2019 and June 2024. Candidate predictors included demographic characteristics, comorbidities and medical history, tumor-related factors, treatment-related factors, and laboratory parameters. The primary endpoint was the occurrence of VTE within six months after hospitalization for confirmed lymphoma. Model development incorporated 3 imputation methods, 3 sampling strategies, 3 feature selection approaches, and 9 machine learning algorithms. Predictive performance was compared across all models. Results: Combining different imputation, sampling, and feature selection strategies yielded 27 datasets, which were trained across 9 algorithms to generate 243 models. The optimal model—Simp-SMOTE_rf_GBM, constructed using random forest imputation, SMOTE oversampling, and gradient boosting machine—achieved the highest predictive performance (AUC=0.954). SHAP-based model interpretation identified 9 key predictors ranked by importance: anticoagulant use, D-dimer, lactate dehydrogenase, central venous catheterization, carcinoembryonic antigen (CEA), Eastern Cooperative Oncology Group (ECOG) score, serum total protein (TP), total cholesterol (TC), and infectious disease. Conclusion: This study established and validated a machine learning model for predicting VTE risk in lymphoma patients, with the optimal model demonstrating excellent discriminatory ability (AUC=0.954). The model provides evidence to guide the timing and strategy of anticoagulation, supporting early VTE screening and risk stratification in clinical practice. Its implementation has important implications for improving patient outcomes and advancing public health.